{"id":"https://openalex.org/W4415328863","doi":"https://doi.org/10.48550/arxiv.2505.15417","title":"Robust Multimodal Learning via Entropy-Gated Contrastive Fusion","display_name":"Robust Multimodal Learning via Entropy-Gated Contrastive Fusion","publication_year":2025,"publication_date":"2025-05-21","ids":{"openalex":"https://openalex.org/W4415328863","doi":"https://doi.org/10.48550/arxiv.2505.15417"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.15417","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15417","pdf_url":"https://arxiv.org/pdf/2505.15417","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119958721","display_name":"Leon Chlon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chlon, Leon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119958722","display_name":"Maggie Chlon","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chlon, Maggie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5119981681","display_name":"MarcAntonio M. Awada","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Awada, MarcAntonio M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.843999981880188},{"id":"https://openalex.org/keywords/missing-modalities","display_name":"missing modalities","score":0.6679999828338623},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.6800000071525574},{"id":"https://openalex.org/keywords/calibration","display_name":"calibration","score":0.574999988079071},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.44600000977516174},{"id":"https://openalex.org/keywords/ms-coco","display_name":"MS COCO","score":0.9879999756813049}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6990000009536743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614999771118164},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6385999917984009},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6233999729156494},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.3968999981880188},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.15417","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15417","pdf_url":"https://arxiv.org/pdf/2505.15417","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.15417","doi":"https://doi.org/10.48550/arxiv.2505.15417","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15417","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15417","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15417","pdf_url":"https://arxiv.org/pdf/2505.15417","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415328863.pdf","grobid_xml":"https://content.openalex.org/works/W4415328863.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7219669939","https://openalex.org/W7202134681","https://openalex.org/W7162696227","https://openalex.org/W4402716394","https://openalex.org/W7128822134","https://openalex.org/W7164866797","https://openalex.org/W7161248753","https://openalex.org/W7127939107","https://openalex.org/W7223153315","https://openalex.org/W4323065956"],"abstract_inverted_index":{"Real-world":[0],"multimodal":[1,114],"systems":[2],"routinely":[3],"face":[4],"missing-input":[5],"scenarios,":[6],"and":[7,64,76],"in":[8,13],"reality,":[9],"robots":[10],"lose":[11],"audio":[12],"a":[14,17,44,67,86],"factory":[15],"or":[16,32],"clinical":[18],"record":[19],"omits":[20],"lab":[21],"tests":[22],"at":[23,85],"inference":[24],"time.":[25],"Standard":[26],"fusion":[27],"layers":[28],"either":[29],"preserve":[30],"robustness":[31],"calibration":[33,59],"but":[34],"never":[35],"both.":[36],"We":[37],"introduce":[38],"Adaptive":[39],"Entropy-Gated":[40],"Contrastive":[41],"Fusion":[42],"(AECF),":[43],"single":[45],"light-weight":[46],"layer":[47,110],"that":[48],"(i)":[49],"adapts":[50],"its":[51],"entropy":[52],"coefficient":[53],"per":[54],"instance,":[55],"(ii)":[56],"enforces":[57],"monotone":[58],"across":[60],"all":[61],"modality":[62],"subsets,":[63],"(iii)":[65],"drives":[66],"curriculum":[68],"mask":[69],"directly":[70],"from":[71],"training-time":[72],"entropy.":[73],"On":[74],"AV-MNIST":[75],"MS-COCO,":[77],"AECF":[78,106],"improves":[79],"masked-input":[80],"mAP":[81],"by":[82,93],"+18":[83],"pp":[84],"50%":[87],"drop":[88],"rate":[89],"while":[90],"reducing":[91],"ECE":[92],"up":[94],"to":[95],"200%,":[96],"yet":[97],"adds":[98],"1%":[99],"run-time.":[100],"All":[101],"back-bones":[102],"remain":[103],"frozen,":[104],"making":[105],"an":[107],"easy":[108],"drop-in":[109],"for":[111],"robust,":[112],"calibrated":[113],"inference.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2025-10-19T00:00:00"}